© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 128975
    Prev
    Next
    INDEX
    Explanations

    occurrences of public speaking events or statements made in formal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    615
    -0.07
     Colonial
    -0.07
    ey
    -0.06
    @nate
    -0.06
     Rosenstein
    -0.06
    FTA
    -0.06
    eyn
    -0.06
     Morrow
    -0.06
    585
    -0.06
    065
    -0.06
    POSITIVE LOGITS
    ego
    0.06
     recom
    0.06
    _RT
    0.06
     moo
    0.06
     trending
    0.06
    vrier
    0.06
    ano
    0.06
    jug
    0.06
    меж
    0.06
    ÏĥÏĢ
    0.06
    Activations Density 0.009%

    No Known Activations